© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79918
    Prev
    Next
    INDEX
    Explanations

    concerning specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     základní
    -1.02
    Răsp
    -0.97
     మరి
    -0.96
    igail
    -0.92
     miasto
    -0.92
     manguera
    -0.92
     čtyř
    -0.91
     několika
    -0.91
     enchufe
    -0.90
    ardless
    -0.90
    POSITIVE LOGITS
     in
    1.63
     of
    1.51
     regarding
    1.48
     for
    1.34
    เกี่ยวกับ
    1.33
     about
    1.27
    关于
    1.20
     concerning
    1.10
     seksual
    1.03
     on
    1.02
    Activations Density 0.259%

    No Known Activations